Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    either/or

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    y
    1.03
    ט
    1.02
    ﺐ
    0.95
    ów
    0.93
    ורים
    0.91
    들도
    0.91
    tage
    0.90
    יה
    0.87
    يات
    0.87
    دى
    0.86
    POSITIVE LOGITS
    もしくは
    0.88
    ли
    0.86
    かの
    0.85
    إ
    0.77
    ेश
    0.76
     Seja
    0.75
    κ
    0.75
    あるいは
    0.73
    械
    0.73
    𝒄
    0.73
    Act Density 0.003%

    No Known Activations